1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
from unittest import TestCase
from protego import _RuleSet
rs = _RuleSet(None)
def _unquote(url, ignore='', errors='replace'):
global rs
return rs._unquote(url, ignore, errors)
def hexescape(char):
global rs
return rs.hexescape(char)
class TestUnquote(TestCase):
"""Tests for unquote()"""
def test_unquoting(self):
# Make sure unquoting of all ASCII values works
escape_list = []
for num in range(128):
given = hexescape(chr(num))
expect = chr(num)
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
escape_list.append(given)
escape_string = ''.join(escape_list)
del escape_list
result = _unquote(escape_string)
self.assertEqual(result.count('%'), 1,
"using unquote(): not all characters escaped: "
"%s" % result)
def test_unquoting_badpercent(self):
# Test unquoting on bad percent-escapes
given = '%xab'
expect = given
result = _unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
given = '%x'
expect = given
result = _unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
given = '%'
expect = given
result = _unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
def test_unquoting_parts(self):
# Make sure unquoting works when have non-quoted characters
# interspersed
given = 'ab%sd' % hexescape('c')
expect = "abcd"
result = _unquote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
def test_unquoting_plus(self):
# Test difference between unquote() and unquote_plus()
given = "are+there+spaces..."
expect = given
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
def test_unquote_with_unicode(self):
# Characters in the Latin-1 range, encoded with UTF-8
given = 'br%C3%BCckner_sapporo_20050930.doc'
expect = u'br\u00fcckner_sapporo_20050930.doc'
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Characters in the Latin-1 range, encoded with None (default)
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Characters in BMP, encoded with UTF-8
given = "%E6%BC%A2%E5%AD%97"
expect = u"\u6f22\u5b57" # "Kanji"
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence
given = "%F3%B1"
expect = u"\ufffd" # Replacement character
result = _unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence, replace errors
result = _unquote(given, errors="replace")
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence, ignoring errors
given = "%F3%B1"
expect = ""
result = _unquote(given, errors="ignore")
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# A mix of non-ASCII and percent-encoded characters, UTF-8
result = _unquote(u"\u6f22%C3%BC")
expect = u'\u6f22\u00fc'
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
def test_escape_sequence_uppercase(self):
result = _unquote('%2fabc%7exyz', ignore='/~')
expect = "%2Fabc%7Exyz"
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
|
